© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43140
    Prev
    Next
    INDEX
    Explanations

    Related to success

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rather
    -0.31
     Rather
    -0.31
    ented
    -0.30
    worked
    -0.30
     plutôt
    -0.29
     rather
    -0.29
    æīĭæĮĩ
    -0.28
     worked
    -0.28
    å·¥ä½ľçļĦ
    -0.28
    itel
    -0.28
    POSITIVE LOGITS
     accomplishment
    0.29
     excellence
    0.29
     future
    0.28
     success
    0.27
     accomplishments
    0.26
    irs
    0.26
    绩
    0.26
     strength
    0.26
     secured
    0.26
     securing
    0.26
    Activations Density 0.005%

    No Known Activations